HistDiT introduces a structure-aware latent conditional DiT with dual-stream conditioning and multi-objective loss that outperforms GANs and U-Net diffusion models for high-fidelity virtual histological staining.
IEEE Transaction on Medical Imaging42(12), 3524–3539 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology
HistDiT introduces a structure-aware latent conditional DiT with dual-stream conditioning and multi-objective loss that outperforms GANs and U-Net diffusion models for high-fidelity virtual histological staining.